FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning

N Cho, N Srishankar, L Cecchi, W Watson - Proceedings of the 5th ACM …, 2024 - dl.acm.org
Financial intelligence generation from vast data sources has typically relied on traditional
methods of knowledge-graph construction or database engineering. Recently, fine-tuned …

Self-Supervised Prompt Optimization

J **ang, J Zhang, Z Yu, F Teng, J Tu, X Liang… - arxiv preprint arxiv …, 2025 - arxiv.org
Well-designed prompts are crucial for enhancing Large language models'(LLMs) reasoning
capabilities while aligning their outputs with task requirements across diverse domains …

StressPrompt: Does Stress Impact Large Language Models and Human Performance Similarly?

G Shen, D Zhao, A Bao, X He, Y Dong… - arxiv preprint arxiv …, 2024 - arxiv.org
Human beings often experience stress, which can significantly influence their performance.
This study explores whether Large Language Models (LLMs) exhibit stress responses …

Boosting Self-Efficacy and Performance of Large Language Models via Verbal Efficacy Stimulations

R Chen, T Peng, X **e, D Lin, Z Cui, Z Chen - arxiv preprint arxiv …, 2025 - arxiv.org
Significant improvements have been observed in the zero-shot capabilities of the Large
Language Models (LLMs). Due to their high sensitivity to input, research has increasingly …

Influence of Solution Efficiency and Valence of Instruction on Additive and Subtractive Solution Strategies in Humans and GPT-4

L Uhler, V Jordan, J Buder, M Huff… - arxiv preprint arxiv …, 2024 - arxiv.org
Generative artificial intelligences, particularly large language models (LLMs), play an
increasingly prominent role in human decision-making contexts, necessitating transparency …

Enhancing the Creativity of Large Language Models through Emotional Stimuli

JH Kim, G Jeong, HS Kim - Annual Conference on Human and …, 2024 - koreascience.kr
거대 언어 모델 (LLM) 의 발전으로 인해 정형화된 작업을 넘어서 창의적인 답변을 생성하는
것이 가능해지면서, LLM 의 창의성을 평가하고 향상시키기 위한 연구가 활발히 진행되고 있다 …